Leveraging Object Proposals for Object-Level Change Detection

Sugimoto, Takashige; Kanji, Tanaka; Yamaguchi, Kousuke

doi:10.1109/ivs.2018.8500475

Cited by 4 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(4) SIFT+NBNN is based on the scene representation of a bag of 128-dim SIFT features [37] with Harris-Laplace keypoints (1,500-2,000 per image) using the naive Bayes nearest neighbor (NBNN) distance metric [38]. (5) LCF+NBNN is different from SIFT+NBNN only in that the 512-dim LCF feature [39] (768 per image) is used instead of the 128-dim SIFT. (6) AE+L2 is based on a global 3,136-dim autoencoder (AE) feature with the nearest neighbor-based distance metric [40].…”

Section: A Comparing Methodsmentioning

confidence: 99%

Exploring Self-Attention for Visual Intersection Classification

Nakata¹,

Takeda²

2022

Preprint

View full text Add to dashboard Cite

In robot vision, self-attention has recently emerged as a technique for capturing non-local contexts. In this study, we introduced a self-attention mechanism into the intersection recognition system as a method to capture the non-local contexts behind the scenes. An intersection classification system comprises two distinctive modules: (a) a first-person vision (FPV) module, which uses a short egocentric view sequence as the intersection is passed, and (b) a third-person vision (TPV) module, which uses a single view immediately before entering the intersection. The self-attention mechanism is effective in the TPV module because most parts of the local pattern (e.g., road edges, buildings, and sky) are similar to each other, and thus the use of a non-local context (e.g., the angle between two diagonal corners around an intersection) would be effective. This study makes three major contributions. First, we proposed a self-attention-based approach for intersection classification using TPVs. Second, we presented a practical system in which a self-attention-based TPV module is combined with an FPV module to improve the overall recognition performance. Finally, experiments using the public KITTI dataset show that the above self-attention-based system outperforms conventional recognition based on local patterns and recognition based on convolution operations.

show abstract

Section: A Comparing Methodsmentioning

confidence: 99%

Exploring Self-Attention for Visual Intersection Classification

Nakata¹,

Takeda²

2022

Preprint

View full text Add to dashboard Cite

show abstract

Detection-by-Localization: Maintenance-Free Change Object Detector

Kanji

2019

2019 International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Recent researches demonstrate that self-localization performance is a very useful measure of likelihood-of-change (LoC) for change detection. In this paper, this "detection-by-localization" scheme is studied in a novel generalized task of object-level change detection. In our framework, a given query image is segmented into object-level subimages (termed "scene parts"), which are then converted to subimage-level pixel-wise LoC maps via the detection-by-localization scheme. Our approach models a self-localization system as a ranking function, outputting a ranked list of reference images, without requiring relevance score. Thanks to this new setting, we can generalize our approach to a broad class of self-localization systems. Our ranking based self-localization model allows to fuse self-localization results from different modalities via an unsupervised rank fusion derived from a field of multi-modal information retrieval (MMR). This study is a first step towards a maintenance-free approach, minimizing maintenance cost of map maintenance system (e.g., background model, detector engine).We would like to express our sincere gratitude to Takuma Sugimoto, Rino Ide and Kousuke Yamaguchi for development of deep learning architecture, and initial investigation on change detection tasks on the dataset, which helped us to focus on our Detection-by-Localization project.

show abstract

Deep Intersection Classification Using First and Third Person Views

Takeda

Kanji

2019

2019 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

Leveraging Object Proposals for Object-Level Change Detection

Cited by 4 publications

References 18 publications

Exploring Self-Attention for Visual Intersection Classification

Exploring Self-Attention for Visual Intersection Classification

Detection-by-Localization: Maintenance-Free Change Object Detector

Deep Intersection Classification Using First and Third Person Views

Contact Info

Product

Resources

About